code-review-ai-ai-review

You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C

Quality

37%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/code-review-ai-ai-review/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is rich with executable, multi-language examples and a real CI/CD integration, making it actionable, but it is far too long and padded with knowledge Claude already has plus stale, time-sensitive model identifiers. Its one progressive-disclosure reference is broken, and the workflows lack explicit validation feedback loops.

Suggestions

Cut the explanatory concept sections (SOLID, OWASP Top 10 list, anti-pattern definitions, scalability red-flag glossary) — Claude already knows these; keep only the task-specific checklists and code.

Move stale, time-sensitive model/version identifiers into an explicitly labeled 'model selection / keep current' note or remove them, since they are already inconsistent (claude-3.7-sonnet vs claude-3-5-sonnet-20241022) and will date the skill.

Fix or remove the broken 'resources/implementation-playbook.md' reference, and add explicit validate->fix->retry checkpoints to the review workflow where it gates merges on critical findings.

Dimension	Reasoning	Score
Conciseness	The ~450-line body is heavily padded and explains concepts Claude already knows (SOLID principles, the OWASP Top 10 list, N+1 queries, what anti-patterns are), and it embeds time-sensitive, already-stale model/version identifiers ('Claude 4.5 Sonnet', 'GPT-5', '2025', 'claude-3.7-sonnet', 'claude-3-5-sonnet-20241022') inline rather than in a deprecated section.	1 / 3
Actionability	It provides large amounts of concrete, copy-paste-ready code in Python, TypeScript, Go, YAML, and bash (e.g. the CodeReviewOrchestrator, the GitHub Actions workflow, the TruffleHog secret-scan one-liner) that directly implement the review steps, satisfying the 'fully executable' anchor.	3 / 3
Workflow Clarity	Multi-step processes are sequenced (Initial Triage -> Multi-Tool Static Analysis -> AI-Assisted Review -> Comment Generation) and there is a quality-gate checkpoint at the end, but validation/feedback loops are otherwise implicit (no 'validate then fix then retry' guidance for the review operations the rubric treats as fragile).	2 / 3
Progressive Disclosure	Sections are organized, but the single external reference points to 'resources/implementation-playbook.md' which does not exist (no references/ directory), and content that could live in separate files (full reference workflows, prompt templates) is inlined, so disclosure is only partially structured.	2 / 3
	Total	8 / 12 Passed

Description

25%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is truncated, written in second person, and lacks any 'when to use' trigger, so it only partially conveys the skill's purpose and would be hard to match to a user request. It reads as an auto-generated template rather than a tight, natural-language trigger.

Suggestions

Rewrite in third person and complete the sentence; lead with concrete actions such as 'Reviews pull requests across 30+ languages using AI plus static analysis tools (CodeQL, Semgrep, SonarQube).'

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when reviewing pull requests, scanning diffs for bugs or vulnerabilities, or wiring automated code review into CI/CD.'

Drop the tool buzzword list from the description and keep it specific to the review task to reduce overlap with generic DevOps skills.

Dimension	Reasoning	Score
Specificity	It names a domain and a few actions ('automated static analysis, intelligent pattern recognition, and modern DevOps practices') but the language is abstract, the sentence is truncated mid-clause, and the second-person voice ('You are an expert...', 'Leverage AI tools') triggers a one-point specificity penalty per the judging guidelines.	1 / 3
Completeness	It states a partial 'what' (the sentence is cut off at 'GPT-5, C') but provides no 'when to use it' guidance at all; the missing 'Use when...' clause caps completeness at 2 and the truncation weakens even the 'what'.	2 / 3
Trigger Term Quality	There are no natural trigger keywords a user would actually say; it relies on technical jargon ('pattern recognition', 'DevOps practices') and omits any 'use when...' phrasing or common user terms like 'code review' or 'PR review'.	1 / 3
Distinctiveness Conflict Risk	The AI-code-review framing is a recognizable niche, but the generic 'expert specialist' positioning and tool laundry list could overlap with other review/DevOps skills, so it is only somewhat distinguishable.	2 / 3
	Total	6 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/code-review-ai-ai-review/SKILL.md
Commit: a3068b7

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.